system HF staff commited on
Commit
9f6d67d
·
1 Parent(s): 8ae7f45

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-mkh
10
+
11
+ * source group: English
12
+ * target group: Mon-Khmer languages
13
+ * OPUS readme: [eng-mkh](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-mkh/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): kha khm khm_Latn mnw vie vie_Hani
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
21
+ * download original weights: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.zip)
22
+ * test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.test.txt)
23
+ * test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-kha.eng.kha | 0.1 | 0.015 |
30
+ | Tatoeba-test.eng-khm.eng.khm | 0.2 | 0.226 |
31
+ | Tatoeba-test.eng-mnw.eng.mnw | 0.7 | 0.003 |
32
+ | Tatoeba-test.eng.multi | 16.5 | 0.330 |
33
+ | Tatoeba-test.eng-vie.eng.vie | 33.7 | 0.513 |
34
+
35
+
36
+ ### System Info:
37
+ - hf_name: eng-mkh
38
+
39
+ - source_languages: eng
40
+
41
+ - target_languages: mkh
42
+
43
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-mkh/README.md
44
+
45
+ - original_repo: Tatoeba-Challenge
46
+
47
+ - tags: ['translation']
48
+
49
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
50
+
51
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.zip
52
+
53
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-mkh/opus-2020-07-27.test.txt
54
+
55
+ - src_alpha3: eng
56
+
57
+ - tgt_alpha3: mkh
58
+
59
+ - short_pair: en-mkh
60
+
61
+ - chrF2_score: 0.33
62
+
63
+ - bleu: 16.5
64
+
65
+ - brevity_penalty: 1.0
66
+
67
+ - ref_len: 34734.0
68
+
69
+ - src_name: English
70
+
71
+ - tgt_name: Mon-Khmer languages
72
+
73
+ - train_date: 2020-07-27
74
+
75
+ - src_alpha2: en
76
+
77
+ - tgt_alpha2: mkh
78
+
79
+ - prefer_old: False
80
+
81
+ - long_pair: eng-mkh
82
+
83
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
84
+
85
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
86
+
87
+ - port_machine: brutasse
88
+
89
+ - port_time: 2020-08-18-01:48